python时间序列预测的真实值和预测值的对比图怎么画

类似于这种图，怎么在lasso回归之后画出这种图，下面是代码

```python
import pandas as pd
import numpy as np
from sklearn import model_selection
from sklearn.linear_model import Lasso, LassoCV
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt

data = pd.read_csv(r'')

#拆分为训练集和测试集
predictors = data.columns[1:]
x_train, x_test, y_train, y_test = model_selection.train_test_split(data[predictors], data.fuel,
                                                               test_size=0.25, random_state=1234)
#构造不同的lambda值
Lambdas = np.logspace(-7, -1, 200)
#设置交叉验证的参数，使用均方误差评估
lasso_cv = LassoCV(alphas=Lambdas, normalize=True, cv=10, max_iter=10000)
lasso_cv.fit(x_train, y_train)

#基于最佳lambda值建模
lasso = Lasso(alpha=lasso_cv.alpha_, normalize=True, max_iter=10000)
lasso.fit(x_train, y_train)
#打印回归系数
print('最优参数：', lasso_cv.alpha_)
print(pd.Series(index=['Intercept']+x_train.columns.tolist(),
                data=[lasso.intercept_]+lasso.coef_.tolist()))

#模型评估
lasso_pred = lasso.predict(x_test)
#均方误差
MSE = mean_squared_error(y_test, lasso_pred)
print('均方误差：', MSE)

train_score = lasso.score(x_train, y_train)  # 模型对训练样本得准确性
test_score = lasso.score(x_test, y_test)  # 模型对测试集的准确性
print(train_score)
print(test_score)

原值和预测值都与时间保持一一对应，设定时间为横轴，保持date要与pre,acc长度一致，试一试看。

不知道你输出的值是什么
修改下图表中y轴的俩个值即可

import matplotlib.pyplot as plt
import numpy as np

x = np.linspace(0, 500, 10)

fig, ax = plt.subplots()  # 创建一个图标

# 修改 x/2+50，x/3 y轴的值
ax.plot(x, x / 2 + 50, label='Actual value')  # 在轴上绘制数据
ax.plot(x, x / 3, label='Predicted value(LASSO)')  # 在轴上绘制数据
ax.set_xlabel('x label')  # 添加x轴标签
ax.set_ylabel('y label')  # 添加y轴标签
ax.set_title("Simple Plot")  # 添加图标标题
ax.legend()  # 添加说明

plt.show()